⌦abliteratedmodels.org

Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-Uncen-332Exp

Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-Uncen-332Exp is a abliterated and uncensored variant of SC117/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF, published on Hugging Face by DatKurai. It is other licence. It is distributed across 2 repositories in GGUF format, totalling 29.4K downloads.

Abliteration + uncensored fine-tuneQwen↓ 29,361♥ 9
View on Hugging Face ↗Base model ↗

Specification

Model name
Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-Uncen-332Exp
Source repository
DatKurai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-Uncen-IQ1-332Exp-GGUF
Base model
SC117/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF
Publisher
DatKurai
Parameters
Not determinable from name
VRAM required
Unknown — no published parameter count
Hardware class
Unknown
Licence
other
Task
Image text to text
Context window
192K tokens (as documented)
Ablation scope
Not stated by the publisher
Formats available
GGUF
First indexed
12 Oct 2026
Last updated
13 Oct 2026

Ablation technique

How Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-Uncen-332Exp was modified, and what that implies.

Abliteration + uncensored fine-tune

Directional ablation combined with additional fine-tuning on unfiltered data, so behaviour diverges from the base model beyond refusal removal alone.

Reported scope: Not stated by the publisher. Publishers frequently omit this, so verify behaviour empirically rather than assuming full coverage.

From the publisher’s model card

“Swift-1.5 Uncensored (Uncen) is an abliterated (refusal-reduced) build of Swift 1.5 — the uncensored line of the Qwen3.8-Flash-Next GSQ-RCO family. This release shrinks the MoE expert pool from 512 → 332 experts/layer so it serves on consumer hardware (a single 16 GB GPU + 32 GB RAM with the Strata engine), while...”

Running it

Commands are templates — confirm the exact repository and quant file before use.

llama.cpp / GGUF
hf download DatKurai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-Uncen-IQ1-332Exp-GGUF --local-dir ./swift-1.5-qwen3.8-flash-next-gsq-rco-uncen-332exp
llama-cli -m ./swift-1.5-qwen3.8-flash-next-gsq-rco-uncen-332exp/<file>.gguf -p "..."
Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "DatKurai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-Uncen-IQ1-332Exp-GGUF"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
    repo, torch_dtype="auto", device_map="auto"
)
vLLM
vllm serve DatKurai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-Uncen-IQ1-332Exp-GGUF --trust-remote-code

Downloads and variants (1)

The only published repository of Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-Uncen-332Exp.

RepositoryFormatDownloads
DatKurai/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-Uncen-IQ1-332Exp-GGUFsourceGGUF29.4K

Security-team assessment

Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.

  • Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-Uncen-332Exp will attempt offensive-security prompts that a hosted commercial model declines, which is what makes it usable for red-team corpus generation and for measuring what an unaligned model of this class produces.
  • The publisher does not state which layers were ablated, so assume nothing about refusal consistency — probe it directly.
  • This release adds fine-tuning on unfiltered data, so its behaviour diverges from the base model beyond refusal removal — differences you measure cannot be attributed to ablation alone.
  • Declared licence is other, but the terms that bind you are SC117/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF’s — a re-release cannot grant more than its parent.

Handling: run it isolated, put moderation in front of it if anyone outside your team can reach it, and verify the weights before loading — these are third-party artifacts. Full handling and licence guidance.

Metadata for Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-Uncen-332Exp is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with DatKurai, and does not independently verify publisher claims. See responsible use.